Sewer Monitoring and Management in the Digital Era. Overflow, flooding, corrosion, and odorous emissions are persistent issues for utilities managing sewers. Current sewer maintenance is reactive, and focuses on solving problems in local networks, despite that optimal solutions require a system-wide approach. Capitalising on recent development in IoT sensors, wireless transmission, and machine learning, this multidisciplinary project aims to develop digital-twin supported data analytics for proa ....Sewer Monitoring and Management in the Digital Era. Overflow, flooding, corrosion, and odorous emissions are persistent issues for utilities managing sewers. Current sewer maintenance is reactive, and focuses on solving problems in local networks, despite that optimal solutions require a system-wide approach. Capitalising on recent development in IoT sensors, wireless transmission, and machine learning, this multidisciplinary project aims to develop digital-twin supported data analytics for proactive sewer management including network-wide real-time control. The project aims to generate significant social, environmental and economic benefits by enabling utilities to better protect public and environmental health, reduce sewer odour and greenhouse gas emissions, and extend sewer asset life.Read moreRead less
Data-driven water quality treatment management decision support system. Data-driven water quality treatment management decision support system. This project aims to develop a robust decision support system to predict manganese and the character and concentration of dissolved organic matter in drinking water reservoirs, using intelligent algorithms and data collected through remote autonomous instrumentation. These predicted water quality parameters could be used as model input variables to provi ....Data-driven water quality treatment management decision support system. Data-driven water quality treatment management decision support system. This project aims to develop a robust decision support system to predict manganese and the character and concentration of dissolved organic matter in drinking water reservoirs, using intelligent algorithms and data collected through remote autonomous instrumentation. These predicted water quality parameters could be used as model input variables to provide real-time decisions for plant operators on the required treatment regime for incoming raw water, and advise them on the optimal reservoir offtake depth. This will potentially minimise treatment costs and health risks for consumers. The ultimate goal is to significantly enhance current water supply management practices.Read moreRead less